defined according to the paths in my workstation. The train and val folders contained png files which were converted from dicom formetted (.dcm) mammography images using the following command
The main.lua first seemed to work fine defining the train metadata, combining all files into a single large file and load the large concatenated list of sample paths to self.imagePath but at this step I received the following error message:
...
/tmp/lua_qJ0uxy
/vol1/apps/torch/7/install/bin/luajit: ...1/apps/torch/7/install/share/lua/5.1/threads/threads.lua:183: [thread 2 callback] /vol1/zafer/software/imagenet-multiGPU.torch/dataset.lua:194: Could not find any image file in the given input paths
stack traceback:
[C]: in function 'assert'
/vol1/zafer/software/imagenet-multiGPU.torch/dataset.lua:194: in function '__init'
/vol1/apps/torch/7/install/share/lua/5.1/torch/init.lua:91: in function </vol1/apps/torch/7/install/share/lua/5.1/torch/init.lua:87>
[C]: in function 'dataLoader'
/vol1/zafer/software/imagenet-multiGPU.torch/donkey.lua:84: in main chunk
[C]: in function 'dofile'
/vol1/zafer/software/imagenet-multiGPU.torch/data.lua:30: in function </vol1/zafer/software/imagenet-multiGPU.torch/data.lua:24>
[C]: in function 'xpcall'
...1/apps/torch/7/install/share/lua/5.1/threads/threads.lua:234: in function 'callback'
/vol1/apps/torch/7/install/share/lua/5.1/threads/queue.lua:65: in function </vol1/apps/torch/7/install/share/lua/5.1/threads/queue.lua:41>
[C]: in function 'pcall'
/vol1/apps/torch/7/install/share/lua/5.1/threads/queue.lua:40: in function 'dojob'
[string " local Queue = require 'threads.queue'..."]:13: in main chunk
stack traceback:
[C]: in function 'error'
...1/apps/torch/7/install/share/lua/5.1/threads/threads.lua:183: in function 'dojob'
...1/apps/torch/7/install/share/lua/5.1/threads/threads.lua:264: in function 'synchronize'
...1/apps/torch/7/install/share/lua/5.1/threads/threads.lua:142: in function 'specific'
...1/apps/torch/7/install/share/lua/5.1/threads/threads.lua:125: in function 'Threads'
/vol1/zafer/software/imagenet-multiGPU.torch/data.lua:19: in main chunk
[C]: in function 'dofile'
/vol1/zafer/software/imagenet-multiGPU.torch/main.lua:37: in main chunk
[C]: in function 'dofile'
...ps/torch/7/install/lib/luarocks/rocks/trepl/scm-1/bin/th:150: in main chunk
[C]: at 0x00405d50
/tmp/lua_cdjLjH
I defined two directories named train and val under my data folder and ran the main.lua code as in the readme only definind the data folder as.
th ${convnet_soumith_dir}main.lua -data $data_dir
where
convnet_soumith_dir="/vol1/zafer/software/imagenet-multiGPU.torch/" data_dir="/vol1/zafer/projects/cancer/breast/data/pilot_images/"
defined according to the paths in my workstation. The train and val folders contained png files which were converted from dicom formetted (.dcm) mammography images using the following command
find . -type f -iname "*.dcm" -print0 | xargs -0 -n 1 -P 24 -I {} convert {} -resize 256x256! {}.png
The main.lua first seemed to work fine defining the train metadata, combining all files into a single large file and load the large concatenated list of sample paths to self.imagePath but at this step I received the following error message: ... /tmp/lua_qJ0uxy /vol1/apps/torch/7/install/bin/luajit: ...1/apps/torch/7/install/share/lua/5.1/threads/threads.lua:183: [thread 2 callback] /vol1/zafer/software/imagenet-multiGPU.torch/dataset.lua:194: Could not find any image file in the given input paths stack traceback: [C]: in function 'assert' /vol1/zafer/software/imagenet-multiGPU.torch/dataset.lua:194: in function '__init' /vol1/apps/torch/7/install/share/lua/5.1/torch/init.lua:91: in function </vol1/apps/torch/7/install/share/lua/5.1/torch/init.lua:87> [C]: in function 'dataLoader' /vol1/zafer/software/imagenet-multiGPU.torch/donkey.lua:84: in main chunk [C]: in function 'dofile' /vol1/zafer/software/imagenet-multiGPU.torch/data.lua:30: in function </vol1/zafer/software/imagenet-multiGPU.torch/data.lua:24> [C]: in function 'xpcall' ...1/apps/torch/7/install/share/lua/5.1/threads/threads.lua:234: in function 'callback' /vol1/apps/torch/7/install/share/lua/5.1/threads/queue.lua:65: in function </vol1/apps/torch/7/install/share/lua/5.1/threads/queue.lua:41> [C]: in function 'pcall' /vol1/apps/torch/7/install/share/lua/5.1/threads/queue.lua:40: in function 'dojob' [string " local Queue = require 'threads.queue'..."]:13: in main chunk stack traceback: [C]: in function 'error' ...1/apps/torch/7/install/share/lua/5.1/threads/threads.lua:183: in function 'dojob' ...1/apps/torch/7/install/share/lua/5.1/threads/threads.lua:264: in function 'synchronize' ...1/apps/torch/7/install/share/lua/5.1/threads/threads.lua:142: in function 'specific' ...1/apps/torch/7/install/share/lua/5.1/threads/threads.lua:125: in function 'Threads' /vol1/zafer/software/imagenet-multiGPU.torch/data.lua:19: in main chunk [C]: in function 'dofile' /vol1/zafer/software/imagenet-multiGPU.torch/main.lua:37: in main chunk [C]: in function 'dofile' ...ps/torch/7/install/lib/luarocks/rocks/trepl/scm-1/bin/th:150: in main chunk [C]: at 0x00405d50 /tmp/lua_cdjLjH
I put those images to my Google Drive. The same set of images were copied to train and val folders: https://drive.google.com/open?id=0B48d1KFhJYFRc3FqeG9oRFVGcFU
Any suggestions? Thanks.